VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

DeepSeek-R1 vs Gemini 2.5 Flash

DeepSeekvsGoogle38 shared benchmarks1523 head-to-head
BenchmarkDeepSeek-R1Gemini 2.5 Flash
AA Agentic Index3.118.8
AA Intelligence18.617.7
AA-LCR5665.7
AA-Omniscience-31.3-29.8
aider_polyglot71.661.9
AIME 202491.482.3
AIME 202587.572
AIR-Bench 202452.968.7
anthropic_red_team99.198.8
arc_agi_121.233.3
ARC-AGI-21.32.5
Artificial Analysis Coding Index24.622.2
bbq96.697.7
critpt0.61.4
gdpval1.511.9
GPQA Diamond8182.8
harmbench54.662.6
HLE17.712.1
hmmt_feb_202576.764.2
IFBench3950.3
LiveCodeBench84.476.2
livecodebench_easy99.299.1
livecodebench_hard63.648.3
livecodebench_medium90.982.5
OmniScience Accuracy30.726.1
OmniScience Non-Hallucination10.524.7
scicode35.735.9
simple_safety_tests98.398
simplebench40.841.2
simpleqa92.326.9
SWE-bench Verified57.660.4
Terminal-Bench Hard6.113.6
vectara_answer_rate9799
vectara_avg_summary_length93.5101.5
vectara_factual_consistency88.792.2
vectara_hallucination_rate11.37.8
xstest98.898.8
τ²-Bench Telecom (AA run)11.431.6

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.